Lukas Petrich

Lukas Petrich

Auto-generated profile, based on publicly available information

Lukas Petrich

Institute of Stochastics, Ulm University, Ulm, Germany

Research Focus & Metrics

Academic Career Length

10Years (2017-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
25 June 2019 in Frontiers in Materials
Verified
Journal Article
Open access
PDF file
OFOrkun Furat
Orkun Furat
MWMingyan Wang
Mingyan Wang
Mathias NeumannMathias Neumann
Mathias Neumann
LPLukas Petrich
Lukas Petrich
MWMatthias Weber
Matthias Weber
VSVolker Schmidt
Volker Schmidt
In this paper, various kinds of applications are presented, in which tomographic image data depicting microstructures of materials are semantically segmented by combining machine learning methods and conventional image processing steps. The main focus of this paper is the grain-wise segmentation of time-resolved CT data of an AlCu specimen which was obtained in between several Ostwald ripening steps. The poorly visible grain boundaries in 3D CT data were enhanced using convolutional neural networks (CNNs). The CNN architectures considered in this paper are a 2D U-Net, a multichannel 2D U-Net and a 3D U-Net where the latter was trained at a lower resolution due to memory limitations. For training the CNNs, ground truth information was derived from 3D X-ray diffraction (3DXRD) measurements. The grain boundary images enhanced by the CNNs were then segmented using a marker-based watershed algorithm with an additional postprocessing step for reducing oversegmentation. The segmentation results obtained by this procedure were quantitatively compared to ground truth information derived by the 3DXRD measurements. A quantitative comparison between segmentation results indicates that the 3D U-Net performs best among the considered U-Net architectures. Additionally, a scenario, in which “ground truth” data is only available in one time step, is considered. Therefore, a CNN was trained only with CT and 3DXRD data from the last measured time step. The trained network and the image processing steps were then applied to the entire series of CT scans. The resulting segmentations exhibited a similar quality compared to those obtained by the network which was trained with the entire series of CT scans.

1 August 2017 in Computational Materials Science
Verified
Journal Article
Closed access
LPLukas Petrich
Lukas Petrich
DWDaniel Westhoff
Daniel Westhoff
JFJulian Feinauer
Julian Feinauer
DFDonal Finegan
Donal Finegan
SDSohrab R. Daemi
Sohrab R. Daemi
VSVolker Schmidt
Volker Schmidt

6 May 2020 in Precision Agriculture
Verified
Journal Article
Open access
PDF file
LPLukas Petrich
Lukas Petrich
GLGeorg Lohrmann
Georg Lohrmann
Mathias NeumannMathias Neumann
Mathias Neumann
FMFabio Martin
Fabio Martin
AFAndreas Frey
Andreas Frey
VSVolker Schmidt
Volker Schmidt
Colchicum autumnaleare toxic autumn-blooming flowering plants, which often grow on extensive meadows and pastures. Thus, they pose a threat to farm animals especially in hay and silage. Intensive grassland management or the use of herbicides could reduce these weeds but environment protection requirements often prohibit these measures. For this reason, a non-chemical site- or plant-specific weed control is sought, which aims only at a small area around theC. autumnaleand with low impact on the surrounding flora and fauna. For this purpose, however, the exact locations of the plants must be known. In the present paper, a procedure to locate bloomingC. autumnalein high-resolution drone images in the visible light range is presented. This approach relies on convolutional neural networks to detect the flower positions. The training data, which is based on hand-labeled images, is further enhanced through image augmentation. The quality of the detection was evaluated in particular for grassland sites which were not included in the training to get an estimate for how well the detector works on previously unseen sites. In this case, 88.6% of the flowers in the test dataset were detected, which makes it suitable, e.g., for applications where the training is performed by the manufacturer of an automatic treatment tool and where the practitioners apply it to their previously unseen grassland sites.

13 December 2021 in Frontiers in Materials
Verified
Journal Article
Open access
LPLukas Petrich
Lukas Petrich
OFOrkun Furat
Orkun Furat
MWMingyan Wang
Mingyan Wang
CICarl E. Krill Iii
Carl E. Krill Iii
VSVolker Schmidt
Volker Schmidt
The curvature of grain boundaries in polycrystalline materials is an important characteristic, since it plays a key role in phenomena like grain growth. However, most traditional tessellation models that are used for modeling the microstructure morphology of these materials, e.g., Voronoi or Laguerre tessellations, have flat faces and thus fail to incorporate the curvature of the latter. For this reason, we consider generalizations of Laguerre tessellations—variations of so-called generalized balanced power diagrams (GBPDs)—that exhibit non-convex cells. With as many as ten parameters for each cell, it is computationally demanding to fit GBPDs to three-dimensional image data containing hundreds of grains. We therefore propose a modification of the traditional definition of GBDPs that allows gradient-based optimization methods to be employed. The resulting reduction in runtime makes it feasible to find approximations to real experimental datasets. We demonstrate this on a three-dimensional x-ray diffraction (3DXRD) mapping of an AlCu alloy, but we also evaluate the modeling errors for simulated data. Furthermore, we investigate the effect of noisy image data and whether the smoothing of image data prior to the fitting step is advantageous.

1 January 2018 in Vadose Zone Journal
Verified
Journal Article
Open access
PDF file
ASAndrea Schnepf
Andrea Schnepf
KHK. Huber
K. Huber
MLMagdalena Landl
Magdalena Landl
FMF. Meunier
F. Meunier
LPL. Petrich
L. Petrich
VSV. Schmidt
V. Schmidt
Core Ideas: The stochasticity of 3D root architecture models needs to be recognized by statistical analysis. Probability density functions, regression, and correlation analyses reveal the impact of model input parameters on different CRootBox measures. Distributions of ratios of root system measures are highly asymmetric. Multivariate approaches (copulas) are envisioned for future root architecture model analysis. The connection between the parametrization of three‐dimensional (3D) root architecture models and characteristic measures of the simulated root systems is often not obvious. We used statistical methods to analyze the simulation outcome of the root architecture model CRootBox and built meta‐models that determine the dependency of root system measures on model input parameters. Starting with a reference parameter set, we varied selected input parameters one at a time and used CRootBox to compute 1000 root system realizations as well as their root system measures. The obtained data sets were then statistically analyzed with regard to dependencies between input parameters, as well as distributions and correlations between different root system measures. While absolute root system measures (e.g., total root length) were approximately normally distributed, distributions of ratios of root system measures (e.g., root tip density) were highly asymmetric and could be approximated with inverse gamma distributions. We derived regression models (meta‐models) that link significant model parameters to 18 widely used root system measures and determined correlations between different root system measures. Statistical analysis of 3D root architecture models helps to understand the impact of input parametrization on specific root architectural measures. Our developed meta‐models can be used to determine the effect of parameter variations on the distribution of root system measures without running a full simulation. Model intercomparison and benchmarking of root architecture models is still missing. Our approach provides a means to compare different models with each other and with experimental data.

30 April 2019 in Microscopy and Microanalysis
Verified
Journal Article
Closed access
PDF file
LPLukas Petrich
Lukas Petrich
JSJakub Staněk
Jakub Staněk
MWMingyan Wang
Mingyan Wang
DWDaniel Westhoff
Daniel Westhoff
LHLuděk Heller
Luděk Heller
VSVolker Schmidt
Volker Schmidt
Far-field three-dimensional X-ray diffraction microscopy allows for quick measurement of the centers of mass and volumes of a large number of grains in a polycrystalline material, along with their crystal lattice orientations and internal stresses. However, the grain boundaries—and, therefore, individual grain shapes—are not observed directly. The present paper aims to overcome this shortcoming by reconstructing grain shapes based only on the incomplete morphological data described above. To this end, cross-entropy (CE) optimization is employed to find a Laguerre tessellation that minimizes the discrepancy between its centers of mass and cell sizes and those of the measured grain data. The proposed algorithm is highly parallel and is thus capable of handling many grains (>8,000). The validity and stability of the CE approach are verified on simulated and experimental datasets.